From 6aa7de059173a986114ac43b8f50b297a86f09a8 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 23 Oct 2017 14:07:29 -0700 Subject: locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland Signed-off-by: Paul E. McKenney Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- lib/assoc_array.c | 20 ++++++++++---------- lib/dynamic_queue_limits.c | 2 +- lib/llist.c | 2 +- lib/vsprintf.c | 4 ++-- 4 files changed, 14 insertions(+), 14 deletions(-) (limited to 'lib') diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 155c55d8db5f..fe7953aead82 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -39,7 +39,7 @@ begin_node: /* Descend through a shortcut */ shortcut = assoc_array_ptr_to_shortcut(cursor); smp_read_barrier_depends(); - cursor = ACCESS_ONCE(shortcut->next_node); + cursor = READ_ONCE(shortcut->next_node); } node = assoc_array_ptr_to_node(cursor); @@ -55,7 +55,7 @@ begin_node: */ has_meta = 0; for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); has_meta |= (unsigned long)ptr; if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer @@ -89,7 +89,7 @@ continue_node: smp_read_barrier_depends(); for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); if (assoc_array_ptr_is_meta(ptr)) { cursor = ptr; goto begin_node; @@ -98,7 +98,7 @@ continue_node: finished_node: /* Move up to the parent (may need to skip back over a shortcut) */ - parent = ACCESS_ONCE(node->back_pointer); + parent = READ_ONCE(node->back_pointer); slot = node->parent_slot; if (parent == stop) return 0; @@ -107,7 +107,7 @@ finished_node: shortcut = assoc_array_ptr_to_shortcut(parent); smp_read_barrier_depends(); cursor = parent; - parent = ACCESS_ONCE(shortcut->back_pointer); + parent = READ_ONCE(shortcut->back_pointer); slot = shortcut->parent_slot; if (parent == stop) return 0; @@ -147,7 +147,7 @@ int assoc_array_iterate(const struct assoc_array *array, void *iterator_data), void *iterator_data) { - struct assoc_array_ptr *root = ACCESS_ONCE(array->root); + struct assoc_array_ptr *root = READ_ONCE(array->root); if (!root) return 0; @@ -194,7 +194,7 @@ assoc_array_walk(const struct assoc_array *array, pr_devel("-->%s()\n", __func__); - cursor = ACCESS_ONCE(array->root); + cursor = READ_ONCE(array->root); if (!cursor) return assoc_array_walk_tree_empty; @@ -220,7 +220,7 @@ consider_node: slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK); slot &= ASSOC_ARRAY_FAN_MASK; - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); pr_devel("consider slot %x [ix=%d type=%lu]\n", slot, level, (unsigned long)ptr & 3); @@ -294,7 +294,7 @@ follow_shortcut: } while (sc_level < shortcut->skip_to_level); /* The shortcut matches the leaf's index to this point. */ - cursor = ACCESS_ONCE(shortcut->next_node); + cursor = READ_ONCE(shortcut->next_node); if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) { level = sc_level; goto jumped; @@ -337,7 +337,7 @@ void *assoc_array_find(const struct assoc_array *array, * the terminal node. */ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = ACCESS_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer * and dereferencing the pointer - but only if we are diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index f346715e2255..81770a55cb16 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -20,7 +20,7 @@ void dql_completed(struct dql *dql, unsigned int count) unsigned int ovlimit, completed, num_queued; bool all_prev_completed; - num_queued = ACCESS_ONCE(dql->num_queued); + num_queued = READ_ONCE(dql->num_queued); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); diff --git a/lib/llist.c b/lib/llist.c index ae5872b1df0c..7062e931a7bb 100644 --- a/lib/llist.c +++ b/lib/llist.c @@ -41,7 +41,7 @@ bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, struct llist_node *first; do { - new_last->next = first = ACCESS_ONCE(head->first); + new_last->next = first = READ_ONCE(head->first); } while (cmpxchg(&head->first, first, new_first) != first); return !first; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 86c3385b9eb3..1746bae94d41 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -620,8 +620,8 @@ char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_sp rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { - p = ACCESS_ONCE(d->d_parent); - array[i] = ACCESS_ONCE(d->d_name.name); + p = READ_ONCE(d->d_parent); + array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; -- cgit From 2dcd5adfb7401b762ddbe4b86dcacc2f3de6b97b Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Wed, 25 Oct 2017 17:56:01 +0900 Subject: locking/lockdep: Remove the BROKEN flag from CONFIG_LOCKDEP_CROSSRELEASE and CONFIG_LOCKDEP_COMPLETIONS Now that the performance regression is fixed, re-enable CONFIG_LOCKDEP_CROSSRELEASE=y and CONFIG_LOCKDEP_COMPLETIONS=y. Signed-off-by: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: amir73il@gmail.com Cc: axboe@kernel.dk Cc: darrick.wong@oracle.com Cc: david@fromorbit.com Cc: hch@infradead.org Cc: idryomov@gmail.com Cc: johan@kernel.org Cc: johannes.berg@intel.com Cc: kernel-team@lge.com Cc: linux-block@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-xfs@vger.kernel.org Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1508921765-15396-6-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- lib/Kconfig.debug | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index dfdad67d8f6c..c1e720a22c71 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1092,8 +1092,8 @@ config PROVE_LOCKING select DEBUG_MUTEXES select DEBUG_RT_MUTEXES if RT_MUTEXES select DEBUG_LOCK_ALLOC - select LOCKDEP_CROSSRELEASE if BROKEN - select LOCKDEP_COMPLETIONS if BROKEN + select LOCKDEP_CROSSRELEASE + select LOCKDEP_COMPLETIONS select TRACE_IRQFLAGS default n help -- cgit From e121d64e16484d4a5eba94cd2fa9eb3848b7c9c2 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Wed, 25 Oct 2017 17:56:02 +0900 Subject: locking/lockdep: Introduce CONFIG_BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK=y Add a Kconfig knob that enables the lockdep "crossrelease_fullstack" boot parameter. Suggested-by: Ingo Molnar Signed-off-by: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: amir73il@gmail.com Cc: axboe@kernel.dk Cc: darrick.wong@oracle.com Cc: david@fromorbit.com Cc: hch@infradead.org Cc: idryomov@gmail.com Cc: johan@kernel.org Cc: johannes.berg@intel.com Cc: kernel-team@lge.com Cc: linux-block@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: linux-mm@kvack.org Cc: linux-xfs@vger.kernel.org Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/1508921765-15396-7-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- lib/Kconfig.debug | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c1e720a22c71..2b439a515c30 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1179,6 +1179,21 @@ config LOCKDEP_COMPLETIONS A deadlock caused by wait_for_completion() and complete() can be detected by lockdep using crossrelease feature. +config BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK + bool "Enable the boot parameter, crossrelease_fullstack" + depends on LOCKDEP_CROSSRELEASE + default n + help + The lockdep "cross-release" feature needs to record stack traces + (of calling functions) for all acquisitions, for eventual later + use during analysis. By default only a single caller is recorded, + because the unwind operation can be very expensive with deeper + stack chains. + + However a boot parameter, crossrelease_fullstack, was + introduced since sometimes deeper traces are required for full + analysis. This option turns on the boot parameter. + config DEBUG_LOCKDEP bool "Lock dependency engine debugging" depends on DEBUG_KERNEL && LOCKDEP -- cgit